Name
Abstract | ||
|---|---|---|
We introduce a novel Deep Network architecture that implements the full feature point handling pipeline, that is, detection, orientation estimation, and feature description. While previous works have successfully tackled each one of these problems individually, we show how to learn to do all three in a unified manner while preserving end-to-end differentiability. We then demonstrate that our Deep pipeline outperforms state-of-the-art methods on a number of benchmark datasets, without the need of retraining. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1007/978-3-319-46466-4_28 | COMPUTER VISION - ECCV 2016, PT VI |
Keywords | DocType | Volume |
Local features, Feature descriptors, Deep Learning | Conference | 9910 |
ISSN | Citations | PageRank |
0302-9743 | 110 | 2.25 |
References | Authors | |
30 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kwang Moo Yi | 1 | 271 | 16.65 |
| Eduard Trulls | 2 | 318 | 11.07 |
| Vincent Lepetit | 3 | 6178 | 306.48 |
| Pascal Fua | 4 | 12768 | 731.45 |